Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    large number

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     chunk
    0.55
     portion
    0.46
    Departamento
    0.44
    Chunks
    0.42
    აწილ
    0.40
     Portion
    0.40
    Aurora
    0.38
    ▬▬
    0.38
    部份
    0.38
     Thermodynamic
    0.38
    POSITIVE LOGITS
     numbers
    0.64
    numbers
    0.60
     Numbers
    0.56
     números
    0.53
     numeri
    0.53
    Numbers
    0.48
    數字
    0.48
     संख्याओं
    0.48
    nums
    0.47
     العدد
    0.47
    Act Density 0.010%

    No Known Activations